AI Engineer - - LLM & RAG (Payments / FinTech / US-Based Multinational)

Job Title: AI Engineer - LLM & RAG (Payments / FinTech / US-Based Multinational)

Location: Bangalore / Hyderabad, India ( only On-site options)

Employment Type: Full-time

Experience Required: 1–3 Years

About The Opportunity

We are partnering with a prominent US-based payment transaction and financial technology enterprise that is scaling its state-of-the-art engineering hubs in Bangalore and Hyderabad. Our client processes high-volume global payment transactions, powers robust merchant solutions, and is aggressively integrating next-generation generative artificial intelligence into its core transaction security, fraud detection, customer intelligence, and automated enterprise workflows.

They operate at high velocity—where production-grade reliability, ultra-low latency, and intelligent automation form the backbone of global financial operations.

The Role

As an AI Engineer (LLM & RAG), you will design, build, and deploy production-grade Large Language Model applications and Retrieval-Augmented Generation (RAG) pipelines that power intelligent financial workflows, compliance verification, and transaction analytics.

You won’t just build prototypes; you will architect robust backend AI services that interface with high-throughput transactional databases, optimize vector search performance, fine-tune embedding models, and ensure enterprise-grade security and accuracy. This role sits at the bleeding edge of FinTech and applied AI.

What You’ll Own

LLM Application Architecture: Design and deploy scalable LLM-powered microservices and agentic workflows for payment operations and enterprise support.

Advanced RAG Pipelines: Build, optimize, and maintain end-to-end RAG systems—handling chunking strategies, hybrid search (keyword + vector), re-ranking, and hallucination reduction.

Model Evaluation & Optimization: Benchmark LLMs, evaluate prompt strategies, and optimize inference latency and token efficiency for production environments.

Vector Database Integration: Manage and scale vector search infrastructure (e.g., Qdrant, Typesense, Pinecone, Milvus, or pgvector) for lightning-fast enterprise document retrieval.

Cross-Functional Engineering: Collaborate closely with backend engineers, data platform teams, and product managers to integrate AI features seamlessly into existing payment rails.

Production Observability: Implement monitoring, logging, and guardrails for LLM outputs to ensure strict compliance, data privacy, and security standards.

What We’re Looking For

Experience: 1–3 years of hands-on software engineering experience, with a dedicated focus on building and shipping production-grade LLM and RAG applications.

Core Tech Stack: Strong proficiency in Python, FastAPI/Flask, async programming, and modern backend infrastructure.

AI/ML Tooling: Deep familiarity with LangChain, LlamaIndex, Hugging Face ecosystem, sentence-transformers, and prompt engineering frameworks.

Vector Databases & Search: Hands-on experience with vector stores and semantic search engines (e.g., Qdrant, Typesense, Elasticsearch, Milvus).

FinTech / Enterprise Mindset: Understanding of data security, API design, microservices architecture, and high-availability systems.

High Agency: A maker-builder mentality who thrives in fast-paced environments, experiments fearlessly with local/cloud LLMs, and takes full ownership from code to deployment.

Why Join?

High-Impact FinTech Scale: Build AI solutions that directly impact global payment processing, transaction intelligence, and merchant security.

Cutting-Edge Tech Stack: Work with modern LLMs, vector search, and high-performance backend architectures without legacy constraints.

Growth & Mentorship: Collaborate with world-class engineering leadership across US and Indian tech hubs.

The Perks: Competitive compensation, flexible work culture, continuous learning budgets, and modern tech infrastructure.

Key Skills & Competencies Required

Large Language Models (LLMs) & Prompt Engineering

Retrieval-Augmented Generation (RAG) Architecture

Python, FastAPI & Asynchronous REST APIs

Vector Databases & Semantic Search (Qdrant, Typesense, Pinecone)

LLM Orchestration Frameworks (LangChain, LlamaIndex)

Embedding Models & Sentence-Transformers

Performance Optimization & Inference Latency Reduction

Production Monitoring, Guardrails & LLMOps

FinTech / Payment Domain Understanding

Microservices & Cloud Infrastructure (AWS/GCP/Azure)

Interested candidates may apply directly or reach out to learn more about this exciting mandate.

Skills: search,enterprise,infrastructure,llm,fintech,vector,rag,azure,microservices,design,aws,rest apis,architecture,databases,data,security,python,gcp